optimize-for-gpu

85 / 100 · Low risk

Fine to try.

By mkurman/zorai (GitHub) · coding · 327 stars · scanned at commit 8ea1fc3

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analysis…

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 10 places.

skills/scientific-skills/optimize-for-gpu/references/cucim.md, line 36Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/cudf.md, line 30Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/cugraph.md, line 30Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.

Show 7 more

skills/scientific-skills/optimize-for-gpu/references/cuml.md, line 31Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/cupy.md, line 28Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/cuspatial.md, line 28Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/cuvs.md, line 28Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/cuxfilter.md, line 30Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/numba.md, line 32Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.
skills/scientific-skills/optimize-for-gpu/references/raft.md, line 24Always use `uv add` (never `pip install` or `conda install`) in all install instructions, docstrings, comments, and error messages.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'optimize-for-gpu' ] || [ -L ~/.agents/skills/'optimize-for-gpu' ]; then echo 'A skill folder named optimize-for-gpu already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/mkurman/zorai' "$d" && git -C "$d" checkout --quiet '8ea1fc3ae126b6e103b8508bacd8f5aa60b6f4ad' -- 'skills/scientific-skills/optimize-for-gpu' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/scientific-skills/optimize-for-gpu' ~/.agents/skills/'optimize-for-gpu' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'optimize-for-gpu' ~/.claude/skills/'optimize-for-gpu' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for mkurman/zorai shows the score of its lowest-scoring skill.

SkillTrust badge for mkurman/zorai

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/mkurman/zorai.svg)](https://zalavijaysinh.github.io/skilltrust/repos/mkurman/zorai/)

Score history

Date	Version	Score
2026-11-13	`8ea1fc3`	85